Neurocomputing

Neurocomputing

Introduction

1. Introduction
2. Math basics (optional)
3. Neurons

Linear models

1. Optimization
2. Linear Regression
3. Regularization
4. Linear classification
5. Multi-class classification
6. Learning theory

Deep learning

1. Artificial neural networks
2. Deep neural networks
3. Convolutional neural networks
4. Object detection
5. Semantic segmentation
6. Autoencoders
7. Restricted Boltzmann machines (optional)
8. Generative adversarial networks
9. Recurrent neural networks
10. Attentional neural networks

Neurocomputing

1. Limits of deep learning
2. Hopfield networks
3. Reservoir computing
4. Unsupervised Hebbian learning
5. Spiking neural networks

Exercises

1. Introduction to Python
- 1.1. Notebook
- 1.2. Solution
2. Numpy and Matplotlib
- 2.1. Notebook
- 2.2. Solution
3. Linear regression
- 3.1. Notebook
- 3.2. Solution
4. Multiple Linear Regression
- 4.1. Notebook
- 4.2. Solution
5. Cross-validation
- 5.1. Notebook
- 5.2. Solution
6. Linear classification
- 6.1. Notebook
- 6.2. Solution
7. Softmax classifier
- 7.1. Notebook
- 7.2. Solution
8. Multi-layer perceptron
- 8.1. Notebook
- 8.2. Solution
9. MNIST classification using keras
- 9.1. Notebook
- 9.2. Solution
10. Convolutional neural networks
- 10.1. Notebook
- 10.2. Solution
11. Transfer learning
- 11.1. Notebook
- 11.2. Solution
12. Variational autoencoder
- 12.1. Notebook
- 12.2. Solution
13. Recurrent neural networks
- 13.1. Notebook
- 13.2. Solution

References

1. Bibliography

Powered by Jupyter Book

9. MNIST classification using keras¶

Presentation

Commented solution

previous

8.2. Multi-layer Perceptron

next

9.1. MNIST classification using keras

By Julien Vitay - julien.vitay@informatik.tu-chemnitz.de
© Copyright 2021.

Technische Universität Chemnitz - Faculty of Computer Science - Professorship for Artificial Intelligence